INDEX

Explanations

terms related to testing frameworks and methodologies

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

atan

-0.16

annes

-0.15

merce

-0.15

inder

-0.15

ersh

-0.14

obi

-0.14

iki

-0.14

åİħ

-0.14

ahl

-0.14

 weather

-0.13

POSITIVE LOGITS

 Pound

0.15

erb

0.15

ltra

0.14

mpr

0.14

.isSelected

0.14

ARGV

0.14

abouts

0.13

 kapÄ±

0.13

-leaning

0.13

reesome

0.13

Activations Density 0.026%

terms related to testing frameworks and methodologies

No Comments

No Known Activations